Affective Computing – Bringing Humans and Machines Closer Through Emotions
summary
Overview of methods and concrete results: facial micro‑expression and physiology sensors feed pretrained models like the Azure Face API and the Effectiva SDK to output per‑face emotion scores (examples show 99% surprise, 68% disgust). Psychology anchors include nine universal emotions and appraisal theories. Demonstrations include multi‑face detection, classroom/retail/medical scenarios, and a fairness workflow using the Felon fairness tool that reduces selection disparity from ~15% to ~1.63% while dropping accuracy 84%→82%.
AI-written summary · about
chapters (6)
- 0:00Start
- 33:22The Moral Machine
- 37:33Visualization dashboard
- 39:25Mitigation
- 40:07Integrated with Azure Machine Learning
- 40:50Collective intelligence
related talks
50mAffective Computing
34mEnhancing Customer Experiences with Emotional AI,
11mAmbient Intelligence and Emotionally Intelligent Devices
26mAffective Computing - What is it and why should I care?
39mAI + JavaScript Rocks
27mAI-eye in Augmented Reality
44mThe age of applied AI
20mEmpowering Education and Therapy with Data Science